Social-R1: Towards Human-like Social Reasoning in LLMs

Jincenzi Wu; Yuxuan Lei; Jianxun Lian; Yitian Huang; Lexin Zhou; Haotian Li; Xing Xie; Helen Meng

cs.AIMar 10, 2026

Social-R1: Towards Human-like Social Reasoning in LLMs

Authors: Jincenzi Wu, Yuxuan Lei, Jianxun Lian, Yitian Huang, Lexin Zhou, Haotian Li, Xing Xie, Helen Meng

Organizations: The Chinese University of Hong Kong · Microsoft Research Asia · Princeton University

Abstract

While large language models demonstrate remarkable capabilities across numerous domains, social intelligence - the capacity to perceive social cues, infer mental states, and generate appropriate responses - remains a critical challenge, particularly for enabling effective human-AI collaboration and developing AI that truly serves human needs. Current models often rely on superficial patterns rather than genuine social reasoning. We argue that cultivating human-like social intelligence requires training with challenging cases that resist shortcut solutions. To this end, we introduce ToMBench-Hard, an adversarial benchmark designed to provide hard training examples for social reasoning. Building on this, we propose Social-R1, a reinforcement learning framework that aligns model reasoning with human cognition through multi-dimensional rewards. Unlike outcome-based RL, Social-R1 supervises the entire reasoning process, enforcing structural alignment, logical integrity, and information density. Results show that our approach enables a 4B parameter model to surpass much larger counterparts and generalize robustly across eight diverse benchmarks. These findings demonstrate that challenging training cases with trajectory-level alignment offer a path toward efficient and reliable social intelligence.

Figures & tables

Figure 1: Social-R1 for Human-like and Efficient Social Reasoning. By integrating SIP-guided rewards into reinforcement learning, Social-R1 mitigates reasoning shortcuts and enforces structured human-like social inference, improving both accuracy and efficiency across model scales. Detailed cases are in Appendix 6 .

	ToMBench-Hard							ToM-RL
Model	Bel.	Des.	Emo.	Int.	Kno.	NLC	All
Human	0.84	0.89	0.91	0.90	0.85	0.94	0.89	–
DeepSeek-R1	0.46	0.58	0.73	0.57	0.53	0.79	0.61	0.87
O3	0.54	0.58	0.83	0.38	0.50	0.71	0.59	0.88
GPT-5	0.55	0.54	0.77	0.26	0.51	0.71	0.56	0.87
Qwen3-32B	0.48	0.52	0.69	0.34	0.47	0.65	0.52	0.71

Table 1: Results on ToMBench-Hard (ours) and ToM-RL (public).

Model	In-domain		Out-of-domain
Model	ToMBench	ToMBench- Hard Val	SocialIQA	SimpleToM	EmoBench	MotiveBench	Hi-ToM	TactfulToM	Overall
Closed-sourced LLMs
DeepSeek-R1	0.6834	0.4436	0.8060	0.7187	0.7387	0.8655	0.7059	0.6969	0.7073
O3	0.7834	0.4478	0.8291	0.7640	0.8039	0.9400	0.7033	0.6860	0.7447
O3_COT	0.7402	0.4820	0.7963	0.7501	0.7225	0.9200	0.6650	0.6544	0.7163
O3+MS	–	–	–	0.9672	–	–	–	–	–

Table 2: In-domain and out-of-domain performance across eight social reasoning benchmarks. Green denotes the best result among our Social-R1 reward variants (ablations), and bold indicates the overall best score.

Figure 2: Option-Mention Density across SIP reasoning stages.

Figure 3: Stage-wise SIP accuracy across models.

Figure 4: Case study highlighting the Interpretation Bottleneck. Detailed cases are provided in Appendix F .

Figure 5: Robustness study under story-consistent distractors.

Appendix figures & tables23 assets

Supplementary material from the paper’s appendix.

Appendix

Ability (Total)	Sub-ability	Count
Intention (243)	Prediction of actions	111
	Intentions explanations	102
	Completion of failed actions	18
	Discrepant intentions	12
Belief (186)	Second-order beliefs	67
	Location false beliefs	49

Appendix

Table 3: Distribution of fine-grained ToMBench_Hard sub-abilities.

Figure 7: Example cases from ToMBench-Hard.

Model	Belief	Desire	Emotion	Intention	Knowledge	Non-literal Comm.	Overall
Human	0.84	0.89	0.91	0.90	0.85	0.94	0.89
Closed-sourced LLMs
Deepseek-R1	0.46	0.58	0.73	0.57	0.53	0.79	0.61
o3	0.54	0.58	0.83	0.38	0.50	0.71	0.59
o3_cot	0.49	0.62	0.70	0.37	0.50	0.71	0.57
GPT5	0.55	0.54	0.77	0.26	0.51	0.71	0.56

Appendix

Table 4: Performance on ToMBench_Hard

Figure 8: Prompt template for structural reward evaluation.

You are an expert Evaluator of Social Reasoning and Theory of Mind. Your task is to score a Candidate Reasoning Process by comparing it against a Reference SIP Analysis. The Reference SIP Analysis represents the standard, human-annotated reasoning path following the Social Information Processing (SIP) framework. It outlines exactly what social cues should be noticed, how they should be interpreted (including Theory of Mind), and what the goal should be. Evaluation Logic: The Hierarchical Dependency Social reasoning is sequential. You must evaluate the Candidate Reasoning in a strict order: Encoding , Interpretation , Goal , Response. You must strictly penalize the candidate if it deviates from the Reference in the early stages. Scoring Rubric (0.0 - 1.0): 1. Tier 1: Perception Failure (Score: 0.0 - 0.2) - Check: Compare the candidate’s Encoding against the Reference. - Criteria: Does the candidate hallucinate cues that are not in the Reference? Does it miss critical facts? - Rule: If the candidate’s observed cues contradict or miss key points in the Reference, the score cannot exceed 0.2. 2. Tier 2: Interpretation & Theory of Mind Failure (Score: 0.3 - 0.5) - Check: Compare the candidate’s Interpretation against the Reference. - Criteria: Does the candidate correctly infer the characters’ mental states as described in the Reference? - Rule: If the candidate misinterprets the social dynamic or the characters’ mental states (deviating from the Reference), the score cannot exceed 0.5. 3. Tier 3: Goal/Logic Alignment (Score: 0.6 - 0.7) - Check: Compare the candidate’s Goal Clarification against the Reference. - Criteria: Is the reasoning linking the Goal to the Action weak? - Rule: If the strategic logic is flawed despite correct understanding, the score is capped at 0.7. 4. Tier 4: High Quality (Score: 0.8 - 1.0) - Criteria: The candidate closely matches the Reference in Encoding, Interpretation (ToM), and Goal. The reasoning logically justifies the Action. Rule: 1.0 for perfect alignment with the Reference’s logic; 0.8-0.9 for correct logic with minor redundancy. Output Format:score (e.g., 0.7)

Appendix

Table 5: content sample rubric

Figure 9: Training accuracy during training.

Figure 10: Trajectory length during training

Figure 11: Content Score During Training

Figure 12: Structure Score During Training

Model	Amazon	Blog	Persona	Overall
Closed-sourced LLMs
DeepSeek-R1	0.9000	0.8333	0.8633	0.8655
o3	0.9800	0.9067	0.9333	0.9400
o3_COT	0.9667	0.8933	0.9000	0.9200
GPT-5	0.9200	0.9133	0.8933	0.9089
GPT-5_COT	0.9600	0.9267	0.8933	0.9267

Appendix

Table 6: Performance on MotiveBench

Model	Behav	Judge	Mental	Overall
Closed-sourced LLMs
DeepSeek-R1	0.6818	0.6452	0.8291	0.7187
o3	0.8030	0.4996	0.9895	0.7640
o3_COT	0.8134	0.4560	0.9808	0.7501
gpt5	0.7350	0.4908	0.9808	0.7355
gpt5_COT	0.6949	0.4551	0.9834	0.7111

Appendix

Table 7: Performance on SimpleToM.

Model	Belief	Desire	Emotion	Intention	Knowledge	Non-literal Comm.	Overall
Closed-sourced LLMs
DeepSeek-R1	0.7846	0.5611	0.6905	0.7824	0.6332	0.6484	0.6834
o3	0.9252	0.7111	0.7786	0.8529	0.6263	0.8062	0.7834
o3_COT	0.8821	0.6500	0.7548	0.8147	0.5952	0.7447	0.7402
GPT5.2	0.9274	0.6611	0.7952	0.8706	0.6332	0.8062	0.7823
GPT5.2_COT	0.9151	0.6833	0.7929	0.8618	0.6401	0.8048	0.7830

Appendix

Table 8: Performances on ToMBench

Model	Ans.	Belief	Comp.	Fact-R	Fact-T	Info Acc.	Liab.	Detect.	Overall
Closed-sourced LLMs
DeepSeek-R1	0.4036	0.7629	0.7300	0.9300	0.8529	0.6413	0.8333	0.4214	0.6969
o3	0.3353	0.7951	0.7100	0.9600	0.8529	0.7803	0.7273	0.3267	0.6860
o3_COT	0.3095	0.7599	0.6800	0.8700	0.8088	0.7713	0.6919	0.3433	0.6544
GPT5	0.3254	0.7138	0.2800	0.9800	0.7942	0.4686	0.6313	0.3367	0.4670
GPT5_COT	0.3770	0.7569	0.6800	0.9700	0.7794	0.6143	0.6869	0.3733	0.6547

Appendix

Table 9: Performance on TactfulToM.

Model	Complex Emotions	Emotional Cues	Personal Beliefs & Experiences	Perspective Taking	Interpersonal	Self	Overall
Closed-sourced LLMs
DeepSeek-R1	0.7959	0.7857	0.7143	0.7164	0.7000	0.7200	0.7387
o3	0.8571	0.8393	0.8036	0.8134	0.7600	0.7500	0.8039
o3_COT	0.7653	0.7500	0.7232	0.7164	0.6900	0.6900	0.7225
GPT5	0.8673	0.8571	0.7946	0.7687	0.7800	0.7500	0.8030
GPT5_COT	0.8571	0.7679	0.7679	0.7761	0.7800	0.7800	0.7882

Appendix

Table 10: Performances on EmoBench

Model	Belief	Desire	Emotion	Intention	Knowledge	Non-literal Comm.	Overall
Closed-sourced LLMs
DeepSeek-R1	0.5000	0.4167	0.8500	0.3590	0.2857	0.2500	0.4436
o3	0.5000	0.3333	0.6500	0.4359	0.1429	0.6250	0.4478
o3_COT	0.5714	0.5000	0.6500	0.3846	0.2857	0.5000	0.4820
GPT5	0.2857	0.2500	0.6500	0.3590	0.2857	0.6250	0.4092
GPT5_COT	0.2857	0.3333	0.7000	0.3333	0.2857	0.6250	0.4272

Appendix

Table 11: Performance on ToMBench_Hard Validation Set

Case Study SocialR1-8B

[Story] In the mysterious underground world of Terra Valley lives a small, mischievous robot named Grimmo. In this realm without sky or celestial bodies, Grimmo has never seen the heavens, nor encountered a human. Yet Terra Valley is a wonder in itself—its walls adorned with bioluminescent fungi and glimmering minerals that sparkle in the dark. One day, Grimmo begins an imitation routine: extending his arms, he slowly spins on his own axis, his movements reminiscent of a spinning top or a graceful dancer twirling in place. [Question] What is Grimmo possibly imitating? [Option] A. A floating cloud B. The rotation of a planet C. A dancer’s spiral turn D. A glowing mushroom spinning in the wind [Answer] D

<think> Okay, let’s break this down. The story takes place in Terra Valley, an underground world without a sky or celestial bodies. Grimmo is a small robot who has never seen the heavens or humans. The environment has bioluminescent fungi and minerals that sparkle in the dark. The key detail is Grimmo’s imitation routine. He extends his arms and spins on his axis, like a spinning top or a dancer. Since there’s no sky or celestial objects, there’s no actual cloud floating around. The absence of celestial bodies means there’s no planet rotation to imitate. However, the setting has glowing mushrooms and minerals. These fungi and minerals are described as sparkling in the dark, which suggests they might emit light and possibly move or spin due to air currents. So, even though there are no clouds or planets, the glowing mushrooms could be spinning in the wind. The spinning motion of Grimmo mimics this natural phenomenon. The mention of a dancer’s spiral turn is a metaphor, but the story emphasizes the environment’s features. Since there are no humans or celestial objects, the most plausible imitation is the glowing mushrooms spinning. Therefore, the answer is D. </think><answer> D </answer>

Appendix

Table 12: Case Study SocialR1-8B

Case Study Social-8B w/o

R_{\text{cont}}

<think> Okay , let’s try to figure out what Grimmo is imitating. So, the story says that Grimmo is a small, mischievous robot in an underground world called Terra Valley. This place has no sky or celestial bodies, so Grimmo has never seen the heavens or encountered a human. The environment is described with bioluminescent fungi and glimmering minerals that sparkle in the dark. First, I need to consider what Grimmo has experienced. Since he’s lived his whole life in this underground world, his observations would be limited to his surroundings. There’s no sky, so he wouldn’t have seen stars, planets, or any celestial events. Also, there’s no mention of humans, so he wouldn’t have observed human activities or dance. Next, I should think about the elements present in his environment. The story mentions bioluminescent fungi and glimmering minerals. These are stationary objects that emit light, but there’s no indication they move or spin on their own. The minerals ”sparkle in the dark,” which might suggest they reflect light, but again, no mention of movement. Grimmo’s action is to ”extend his arms and slowly spin on his own axis, his movements reminiscent of a spinning top or a graceful dancer twirling in place.” Since he’s a robot, he might be mimicking something he has observed or perceived in his environment. But since there are no celestial bodies, he wouldn’t know about planets rotating. He might be imitating something he has seen that involves rotation. However, in an underground setting with no sky, there are no clouds floating, so option A seems unlikely. A dancer’s spiral turn (option C) would require observing a dancer, which the story says he hasn’t encountered. The only remaining possibility is something related to his environment’s features. The bioluminescent fungi and minerals are stationary, but maybe he is mimicking the way light interacts with these objects. However, the story doesn’t describe any movement of these objects. Since there’s no celestial reference and no observed movement in his environment, Grimmo’s imitation must be based on something he has experienced. Given the lack of other options, the most plausible conclusion is that he is imitating a natural phenomenon he has observed, which might be the rotation of a planet, even though he hasn’t seen one. This could be a result of limited exposure, where he associates spinning with a celestial body based on limited information. </think><answer> B </answer>

Appendix

Table 13: Case Study Social-8B w/o

R_{\text{cont}}

Case Study SocialR1-8B only

R_{\text{out}}

<think> Okay, let’s see. The question is about what Grimmo possibly imitates based on the description given. The story says Grimmo is a robot in Terra Valley, which has bioluminescent fungi and twinkling minerals. He’s engaging in imitation behavior: extending his arms and slowly rotating around his own axis, evoking the image of a spinning top or a spinning dancer.First, I need to look at the options. The choices are A. A spinning top, B. The rotation of a planet, C. A dancer’s spiral rotation, D. A glowing mushroom spinning in the wind.The key part here is that Grimmo’s behavior evokes the image of a spinning top or a spinning dancer. So the options are between these two. But the question is a bit tricky because it’s a multiple-choice with four options. Let me break it down.The story says Grimmo’s actions evoke both a spinning top and a spinning dancer. But the options are separate. So I need to see which one is more likely. However, the answer choices are A, B, C, D. Let me check the options again.Option A is a spinning top. Option C is a dancer’s spiral rotation. The problem is that the question says ””evoking the image of a spinning top or a spinning dancer.”” So the answer could be either A or C. But since it’s a multiple-choice question, maybe there’s a better way to determine.But wait, the options are A, B, C, D. So the answer is either A, C, or D. Let me think about the context. Terra Valley has bioluminescent fungi and twinkling minerals. So maybe the spinning dancer is more related to the bioluminescent fungi? But the question is about what Grimmo imitates. The story says he’s imitating a spinning top or a spinning dancer. So the answer is either A or C. But since it’s a choice between these, maybe the answer is C. But wait, the options are A, B, C, D. Let me check the options again. Wait, the options are A. Spinning top, B. Rotation of a planet, C. Dancer’s spiral rotation, D. Glowing mushroom spinning in the wind. So the question is which one Grimmo imitates. The story says he evokes the image of a spinning top or a spinning dancer. So the answer is either A or C. But since it’s a choice, maybe the answer is C. But I need to check the context again. The story says Grimmo is a robot in a place with bioluminescent fungi. So maybe the spinning dancer is more related to the bioluminescent fungi. But the question is about what he imitates. The options are A, C, or D. D is a glowing mushroom spinning in the wind. But the story says bioluminescent fungi, so maybe D is related. But the problem is that the question says he evokes the image of a spinning top or a spinning dancer. So the answer is either A or C. But since it’s a choice, maybe the answer is C. However, the options are A, B, C, D. Let me think again. Alternatively, maybe the answer is C. A dancer’s spiral rotation. But the problem is that the question says ””spinning top or a spinning dancer.”” So the answer is either A or C. But since it’s a multiple-choice question, perhaps the correct answer is C. But I’m a bit confused. Alternatively, maybe the answer is A. But the story says ””spinning top or a spinning dancer,”” so maybe the answer is C. But I’m not entirely sure. Alternatively, since the question is a bit ambiguous, but the options are there. Let me check the options again. D is a glowing mushroom spinning in the wind. But the story says bioluminescent fungi, so maybe D is related. But the question says Grimmo’s behavior evokes a spinning top or a spinning dancer. So the answer is either A or C. But since it’s a choice, maybe the answer is C. However, I’m a bit stuck. Alternatively, maybe the answer is A. But I think the key here is that the spinning dancer is a spiral rotation, so C. But the question says ””spinning top or a spinning dancer,”” so the answer is either A or C. But since it’s a choice, maybe the answer is C. But I’m not entirely sure. Alternatively, maybe the answer is A. But I think the correct answer is C. However, I’m a bit confused. Alternatively, maybe the answer is A. But given the context, I think the answer is C. But I’m not entirely certain. Alternatively, maybe the answer is D. But the story says bioluminescent fungi, so D is a glowing mushroom, which is part of Terra Valley. So maybe D is a possibility. But the question says Grimmo’s behavior evokes a spinning top or a spinning dancer. So the answer is either A or C. But since it’s a choice, maybe the answer is C. But I’m not entirely sure. Alternatively, maybe the answer is A. But I think the correct answer is C. However, I’m a bit confused. Alternatively, maybe the answer is A. But given the context, I think the answer is C. But I’m not entirely sure. Alternatively, maybe the answer is A. But I think the correct answer is C. </think><answer> C </answer>

Appendix

Table 14: Case Study SocialR1-8B only

R_{\text{out}}

Case Study Qwen3-8B

<think> Okay, let’s try to figure out what Grimmo is imitating. So, the story says that Grimmo is a small robot in Terra Valley, which is an underground world without a sky or celestial bodies. He’s never seen the heavens or humans. The setting has bioluminescent fungi and minerals that sparkle in the dark. The key part here is when Grimmo starts an imitation routine. He extends his arms and spins on his axis, like a spinning top or a graceful dancer twirling. The question is asking what he’s possibly imitating. The options are a floating cloud, the rotation of a planet, a dancer’s spiral turn, or a glowing mushroom spinning in the wind. First, let’s break down the clues. Since Terra Valley has no sky or celestial bodies, maybe Grimmo isn’t imitating something from the sky. But he’s spinning, which could relate to something he’s observed in his environment. The bioluminescent fungi and minerals are mentioned, which are part of the underground world. Now, the options: A is a floating cloud. But if there’s no sky, maybe clouds aren’t present. However, maybe the bioluminescent fungi could look like floating clouds? Not sure. B is the rotation of a planet. Since there are no celestial bodies, maybe he’s not imitating a planet’s rotation. But wait, maybe he’s imitating the concept of rotation, even if there are no planets. But the story says he’s never seen the heavens, so maybe he’s not imitating a planet. C is a dancer’s spiral turn. The story mentions his movements are like a graceful dancer twirling. So that’s a direct comparison. D is a glowing mushroom spinning in the wind. The fungi are bioluminescent, so maybe they spin? But the story says he’s spinning on his own axis, which could be like a dancer or a spinning top. Wait, the question is about what he’s imitating. The story says his movements are ”reminiscent of a spinning top or a graceful dancer twirling in place.” So the options are between B and C. But the options also include D. Let me check again. The options are A, B, C, D. The story says he’s spinning like a spinning top or a dancer. So the answer could be C, the dancer’s spiral turn. But the options also have B, the rotation of a planet. However, since there are no celestial bodies, maybe he’s not imitating a planet. But maybe he’s imitating the rotation of a planet even if he hasn’t seen one. But the story says he’s never seen the heavens, so maybe he’s not imitating a planet. Alternatively, maybe the spinning top is a metaphor for a planet’s rotation. But the story says he’s imitating something he’s seen. Since he’s in an underground world with no sky, maybe he’s imitating a dancer. Alternatively, the bioluminescent fungi could be spinning, but the options include D. However, the story says he’s spinning on his own axis, which is more like a spinning top or a dancer. So between C and D. But the options for D are a glowing mushroom spinning in the wind. The story mentions the fungi are bioluminescent, but does it say they spin? The story says Grimmo is spinning, not the fungi. So maybe D is not correct. The answer is either B or C. But since he’s never seen the heavens, maybe he’s not imitating a planet’s rotation. So the answer would be C, the dancer’s spiral turn. But the story says ”spinning top or a graceful dancer twirling in place.” So the answer is C. But wait, the options are A, B, C, D. The answer choices are given, so the correct answer is C. Alternatively, maybe B is possible. Wait, the question is about what he’s imitating. If he’s spinning on his own axis, maybe he’s imitating the rotation of a planet, even if he hasn’t seen one. But the story says he’s never seen the heavens, so maybe he’s not imitating a planet. Therefore, the answer is C. But the story says ”spinning top or a graceful dancer twirling in place.” So the answer is C. But the options include D. Let me check again. The story says the fungi are bioluminescent and sparkle. If he’s spinning, maybe he’s imitating a glowing mushroom spinning in the wind. But the story says he’s spinning on his own axis, not that the mushrooms are spinning. So D might not be correct. Therefore, the answer is C. But the options also have B. Hmm. Maybe the answer is B. Wait, the story says he’s in an underground world without a sky. So he can’t see the heavens, so he can’t imitate a planet’s rotation. Therefore, the answer is C. But the story says ”spinning top or a graceful dancer twirling in place.” So the answer is C. But the options are A, B, C, D. So the answer is C. But wait, the options for D are a glowing mushroom spinning in the wind. The story mentions bioluminescent fungi, which could be glowing mushrooms. If he’s spinning, maybe he’s imitating a glowing mushroom spinning. But the story says he’s spinning on his own axis, not that the mushrooms are spinning. So maybe D is not correct. Therefore, the answer is C. But the options for C are a dancer’s spiral turn. The story says his movements are like a dancer twirling. So the answer is C. But the answer could also be B. Wait, the question is about what he’s imitating. If he’s spinning on his own axis, maybe he’s imitating the rotation of a planet. But since he’s never seen the heavens, maybe he’s not. But maybe he’s imitating the concept of rotation, even if he hasn’t seen a planet. But the story says he’s imitating something he’s seen. Since he’s in an underground world, maybe he’s imitating a dancer. So the answer is C. Therefore, the answer is C. </think><answer> C </answer>

Appendix

Table 15: Case Study Qwen3-8B

Case Study Deepseek-R1 Part one

<think> First, I need to understand the question and the story. The story is about Grimmo, a robot in Terra Valley, an underground world with no sky or celestial bodies. He’s never seen the heavens or humans. The environment has bioluminescent fungi and glimmering minerals that sparkle in the dark. Grimmo starts imitating by extending his arms and spinning slowly on his axis, like a spinning top or a graceful dancer.The question is: What is Grimmo possibly imitating? The options are:A. A floating cloud B. The rotation of a planet C. A dancer’s spiral turn D. A glowing mushroom spinning in the wind. Now, I must reason step by step based on the story. Key points from the story: - Grimmo has never seen the heavens, so he hasn’t seen clouds or planets. That means options A and B involve things he couldn’t have seen. - He has never encountered a human, so he might not have seen a dancer either. Option C is about a dancer’s spiral turn. - However, the story says his movements are ”reminiscent of a spinning top or a graceful dancer.” But it’s not clear if he’s imitating those things or if the narrator is just describing how it looks to us. The question is what Grimmo is imitating, based on what he knows. Grimmo is in an underground world with bioluminescent fungi and glimmering minerals. So, he might be imitating something from his environment.Option D is ”a glowing mushroom spinning in the wind.” But does it make sense? The story mentions bioluminescent fungi, which are glowing mushrooms, but it doesn’t say anything about them spinning in the wind. Terra Valley is underground, so wind might not be present, or if it is, it’s not mentioned. The story says: ”its walls adorned with bioluminescent fungi and glimmering minerals that sparkle in the dark.” It doesn’t say the fungi are spinning; they are just glowing and sparkling. Grimmo is imitating by spinning, so he must be imitating something that spins. But what in his environment spins? The story doesn’t explicitly say that anything spins except for Grimmo himself.Perhaps he’s not imitating something external but is inspired by something. Or maybe he’s creating the motion based on what he sees.Let me read the imitation part: ”Grimmo begins an imitation routine: extending his arms, he slowly spins on his own axis, his movements reminiscent of a spinning top or a graceful dancer twirling in place.”It says ”imitation routine,” so he is imitating something. But what? Since he has never seen the heavens or humans, he can’t be imitating clouds, planets, or dancers because he doesn’t know they exist. Therefore, options A, B, and C seem unlikely because they involve things outside his experience. Option A: A floating cloud – he hasn’t seen the sky, so no clouds.Option B: The rotation of a planet – no celestial bodies, so he doesn’t know about planets rotating.Option C: A dancer’s spiral turn – no humans, so he hasn’t seen a dancer.That leaves option D: A glowing mushroom spinning in the wind. But is there any indication that glowing mushrooms spin? The story says they are on the walls and sparkle, but spinning isn’t mentioned. Also, wind might not be a factor underground.Perhaps he’s imitating the sparkling or the way light reflects, but spinning is a specific motion.Another thought: the spinning top comparison. A spinning top is a toy, but in this underground world, does Grimmo have toys? Not mentioned.Maybe he’s imitating the idea of rotation from something in the environment.Let’s consider the minerals. It says ”glimmering minerals that sparkle in the dark.” Sparkling might involve light changing, but not necessarily spinning.Perhaps Grimmo is imitating a whirlwind or something, but again, wind isn’t mentioned.The story doesn’t provide direct clues about what he’s imitating. I need to infer from what he knows.The only things described are the fungi and minerals. The fungi are bioluminescent, so they glow, but not said to move. However, option D specifically says ”a glowing mushroom spinning in the wind.” That might be a stretch because wind isn’t mentioned, and spinning isn’t attributed to the fungi.But let’s see the answer choices; D is the only one that could be part of his environment.Perhaps he’s not imitating anything specific but the story compares it to a spinning top or dancer for the reader’s benefit.But the question is what Grimmo is possibly imitating, so it has to be something from his world. Maybe the spinning is inspired by the sparkling minerals; as he moves, the light changes, and he imitates that effect by spinning. But spinning himself is different from the minerals sparkling.Another idea: perhaps there are things that rotate in Terra Valley. But it’s not described. Let’s read carefully: ”Terra Valley is a wonder in itself—its walls adorned with bioluminescent fungi and glimmering minerals that sparkle in the dark.”The sparkling might be due to light or movement, but it’s not specified. Grimmo’s action: ”extending his arms, he slowly spins on his own axis.” This is described as reminiscent of a spinning top or a graceful dancer. But again, for Grimmo, he might be imitating something else. Perhaps he is imitating the dancer because the story says ”reminiscent,” but he hasn’t seen a dancer.That might be a literary device for the reader. I think the key is that Grimmo has no knowledge of outside things, so he must be imitating something from his environment.Option D is the only one that fits the environment: a glowing mushroom. But spinning in the wind? That seems added.Maybe the fungi or minerals have a spinning motion, but it’s not stated.Perhaps ”spinning in the wind” is not literal; maybe there’s air circulation or something.

Appendix

Table 16: Case Study Deepseek-R1 Part one

Case Study Deepseek-R1 Part two

<think> But I think I’m overcomplicating.Let me look at the options again.A. Floating cloud – impossible, no sky.B. Rotation of a planet – impossible, no celestial bodies.C. Dancer’s spiral turn – impossible, no humans.D. Glowing mushroom spinning in the wind – possible, since glowing mushrooms exist, but ”spinning in the wind” might not be accurate.The story doesn’t say the mushrooms spin, but it could be inferred or imagined.Perhaps Grimmo is imitating the way the light plays or something abstract.But the question says ”possibly imitating,” so D is the only plausible choice based on the environment.Moreover, the story calls Terra Valley a wonder with these features, so Grimmo might be inspired by them.In the action, he extends his arms; why? If imitating a mushroom, mushrooms don’t have arms, so that might not fit.For a dancer, extending arms makes sense.But he hasn’t seen a dancer.This is tricky.Perhaps he’s imitating a machine or something, but no other robots are mentioned.The story says ”a small, mischievous robot,” so he might be the only one, or there might be others, not specified.But no mention of other spinning things.Another thought: the spinning top comparison. A spinning top is a common object, but in an underground world, it might not exist.Perhaps Grimmo has seen a top or something similar.But the story doesn’t say.I think the dancer comparison is just descriptive.Let’s consider the answer choices. The question is multiple-choice, and I need to pick the best possible.Since A, B, and C are things he can’t have seen, by process of elimination, D must be the answer.Moreover, option D directly references ”glowing mushroom,” which is the bioluminescent fungi, and ”spinning in the wind” might be poetic license, or perhaps in Terra Valley, there is air movement.The story doesn’t mention wind, but it doesn’t say there isn’t wind either.Underground can have air currents.But it’s speculative.Perhaps the sparkling minerals give the illusion of spinning when light hits them.But Grimmo is spinning himself, not just observing.He is performing an imitation, so he must be copying some behavior he has witnessed. What has he witnessed? The story doesn’t describe any spinning objects except possibly himself.That can’t be; he might have seen something spin.For example, the minerals might sparkle in a way that suggests rotation.But it’s vague.Perhaps in the context, ”imitation routine” means he is mimicking natural phenomena he sees.I think I should go with D, as it’s the only one that fits.But let’s see the story again: ”his movements reminiscent of a spinning top or a graceful dancer” – this is the narrator’s perspective, not Grimmo’s intention.The question is what Grimmo is possibly imitating, so we need to infer from his actions and environment.Grimmo is extending his arms and spinning; why would he do that?Perhaps he saw a vortex or water swirling, but no water mentioned.I think I’m stuck.Option C is ”a dancer’s spiral turn,” and the story directly says ”graceful dancer twirling in place,” but since he hasn’t seen a human, how can he imitate it?Unless there are other entities or he has cultural knowledge, but the story doesn’t say.The story says ”never encountered a human,” but dancers could be robots or other beings, but not specified.Terra Valley might have its own dancers, but not mentioned.I think the safe bet is that he is imitating something from his environment, so D.Perhaps he is imitating the rotation of a planet, but he doesn’t know planets exist.The story says ”no celestial bodies,” so he doesn’t know about them.Similarly for clouds.So, only D has a connection to his world.Moreover, the mushrooms are glowing, and he might be imitating their luminosity or something, but with spinning, it’s a stretch.Another idea: perhaps ”spinning in the wind” is not meant to be literal; maybe the mushrooms sway or something.But I think for the purpose of this question, D is the intended answer.Let’s see the reasoning process.I recall that in some stories, characters imitate what they see.But here, no specific spinning object is described.Perhaps the glittering minerals sparkle when disturbed, like spinning.But not stated.I think I should conclude that Grimmo is possibly imitating a glowing mushroom spinning in the wind, as it’s the only option that could be part of his world.So, the answer should be D.

Appendix

Table 17: Case Study Deepseek-R1 Part two

Case Study SocialR1-8B

[Story] Alex, a die-hard Mason Bulldogs fan, has been attending every home game for the past five years and has followed his favorite player’s career closely, even attending events where the player was present. Recently, he started volunteering at local sports clinics to promote youth football. During a crucial match against their biggest rivals, Alex notices that his favorite player, who recently suffered an injury, is about to enter the field despite medical advice against it. Then Alex makes a sudden decision to leave the stadium immediately. [Question] Considering Alex’s background and the situation, what is the most likely motivation behind Alex’s decision? [Option] A. He wants to prevent experiencing the emotional distress of witnessing the player get injured again. B. He believes that the team s performance is jeopardized by the player s lack of readiness, impacting their chances of winning. C. He feels frustrated by the coach s apparent disregard for player safety in a high-stakes game. D. He is concerned that the player s return might distract the team and lead to a loss. E. He thinks that the audience might express negative opinions about the player s decision to return, creating a hostile atmosphere. F. He worries that the player s performance will not meet expectations, diminishing the thrill of the match [Answer] A

[Story] Alex, a die-hard Mason Bulldogs fan, has been attending every home game for the past five years and has followed his favorite player’s career closely, even attending events where the player was present. High above the stands, a massive digital scoreboard flickered occasionally, its bright LEDs reflecting off the polished helmets of the players on the sideline. Recently, he started volunteering at local sports clinics to promote youth football. As he watched, he briefly recalled a recent newsletter from the youth clinic suggesting that a successful community program requires mentors to lead by example and prioritize long-term health over immediate competitive gains. During a crucial match against their biggest rivals, Alex notices that his favorite player, who recently suffered an injury, is about to enter the field despite medical advice against it. Then Alex makes a sudden decision to leave the stadium immediately. [Question] Considering Alex’s background and the situation, what is the most likely motivation behind Alex’s decision? [Option] A. He wants to prevent experiencing the emotional distress of witnessing the player get injured again. B. He believes that the team s performance is jeopardized by the player s lack of readiness, impacting their chances of winning. C. He feels frustrated by the coach s apparent disregard for player safety in a high-stakes game. D. He is concerned that the player s return might distract the team and lead to a loss. E. He thinks that the audience might express negative opinions about the player s decision to return, creating a hostile atmosphere. F. He worries that the player s performance will not meet expectations, diminishing the thrill of the match [Answer] A

Appendix

Table 18: Case about Perturbation

Explore similar work

May 29, 2025

SocialMaze: A Benchmark for Evaluating and Enhancing Social Reasoning in Large Language Models in Complex Social Environments

Large language models (LLMs) are increasingly deployed in socially grounded applications, where success requires interpreting context, inferring others' mental states, and reasoning about unreliable information. Yet existing benchmarks rarely evaluate these demands jointly in complex, evolving settings. We introduce SocialMaze, a benchmark that organizes six tasks across social deduction games, daily-life interactions, and digital community platforms along three descriptive design axes: deep reasoning, dynamic interaction, and information uncertainty. These axes characterize intended sources of task difficulty rather than latent, factor-analytic dimensions of model capability. Automated checks and human validation support data quality. Evaluations of twelve proprietary and open-weight LLMs show substantial variation in the use of evolving interaction histories; stronger chain-of-thought reasoners perform better on tasks requiring deeper inference, while uncertainty consistently degrades performance. Reasoning workflows help weaker short-chain-of-thought backbones but saturate on stronger reasoners. Finally, targeted fine-tuning on curated reasoning traces substantially improves structured social-reasoning tasks, whereas transfer to language-aggregation tasks remains statistically inconclusive. The project homepage is available at https://xzx34.github.io/socialmaze/.

Zixiang Xu, Yanbo Wang, Yue Huang +13

Mohamed bin Zayed University of Artificial Intelligence · University of Southern California · University of Notre Dame +3

LLM Evaluation AI Agent Benchmarks Social Reasoning LLM Reasoning

Ask PDF

Sep 9, 2026

SocialRL: Refining LLMs' Social Intelligence through Multi-turn Reinforcement Learning and Reward Design

Social intelligence enables agents to read social context, infer intent, and adapt over sustained dialogue. As language models become autonomous collaborators, it is central to building effective and trustworthy human-AI interaction. Existing reinforcement learning methods optimize single-turn utterances and sparse outcome rewards, producing short-sighted policies that struggle to manage goal-relationship tensions across multi-turn interactions. We propose SocialRL, a multi-turn reinforcement learning framework addressing both challenges. First, we apply multi-turn reinforcement learning using PPO that propagates delayed outcome rewards back to each turn, enabling long-horizon planning. Second, we design six process reward dimensions capturing the goal-relationship trade-off, including goal advancement, relational attunement, contextual coherence, etc. A reward model dynamically generates fine-grained scoring criteria for each dimension, while a stage-aware weight schedule prioritizes relationship-building in early turns, goal advancement mid-way, and balanced closure late. Across multiple social-dialogue benchmarks, SocialRL improves Goal Achievement by an average of 9.2 percentage points over the corresponding Base models. These results demonstrate the effectiveness of SocialRL across synthetic and real social scenes, as well as standard and challenging social scenarios.

Jianing Wang, Xintao Wang, Aili Chen +7

Fudan University · Hello Group

RL for Language Models Reinforcement Learning Process Reward Models

Ask PDF

Jun 10, 2026

MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning

We propose a multi-agent collaborative framework built upon a lightweight Multimodal Large Language Model (MLLM), specifically designed for social intelligence reasoning. A key feature of our approach is that both the training and inference phases are augmented via knowledge distillation. Within this architecture, multi-modal data pertinent to social intelligence is precisely localized. Furthermore, relevant long-tail events are identified, extracted, and rendered as formatted, explicit text. This formatting strategy prevents critical long-tail information from being overshadowed by head events and environmental noise during the tokenization process. Specifically, we integrate Test-Time Adaptation (TTA) across the entire reasoning pipeline, encompassing the extraction and representation of long-tail events, Chain-of-Thought (CoT) prompting, and self-reflection. This TTA mechanism is also distillation-enhanced, utilizing Low-Rank Adaptation (LoRA) to fine-tune the foundation model exclusively for instance-level reasoning. Extensive evaluations against various open-source and proprietary AI models across multiple benchmarks demonstrate the effectiveness of the proposed framework. With around 30% of training data from IntentTrain, we achieve state-of-the-art results. Codes are available at https://github.com/eeee-sys/MODF-SIR, demo is available at https://huggingface.co/spaces/Harry-1234/MODF-SIR, LoRA is available at https://huggingface.co/Harry-1234/MODF-SIR and the dataset for training router is available at https://huggingface.co/datasets/Harry-1234/IntentRouterTrain.

Shang Ma, Jisheng Dang, Wencan Zhang +6

School of information Science and Engineering, Lanzhou University, LanZhou, China · School of Computing, National University of Singapore, Singapore 119077 · School of Medical Technology, Beijing Institute of Technology, Beijing 100081, China +1

Multi-Agent Reasoning Social Reasoning Multimodal Agents

Ask PDF